Value of T2 Mapping MRI for Prostate Cancer Detection and Classification

Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks

OBJECTIVE

Quantitative parameter mapping conventionally relies on curve fitting techniques to estimate parameters from magnetic resonance image series. This study compares conventional curve fitting techniques to methods using neural networks (NN) for measuring T2 in the prostate.

MATERIALS AND METHODS

Large physics-based synthetic datasets simulating T2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Four combinations of different NN architectures and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness.

RESULTS

In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst the methods. On in vivo data, this best performing method produced low-noise T2 maps and showed the least deterioration with increasing input noise levels.

DISCUSSION

This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.

Value of MRI - T2 Mapping to Differentiate Clinically Significant Prostate Cancer

Standardized reporting of multiparametric prostate MRI (mpMRI) is widespread and follows international standards (Pi-RADS). However, quantitative measurements from mpMRI are not widely comparable. Although T2 mapping sequences can provide repeatable quantitative image measurements and extract reliable imaging biomarkers from mpMRI, they are often time-consuming. We therefore investigated the value of quantitative measurements on a highly accelerated T2 mapping sequence, in order to establish a threshold to differentiate benign from malignant lesions. For this purpose, we evaluated a novel, highly accelerated T2 mapping research sequence that enables high-resolution image acquisition with short acquisition times in everyday clinical practice. In this retrospective single-center study, we included 54 patients with clinically indicated MRI of the prostate and biopsy-confirmed carcinoma (n = 37) or exclusion of carcinoma (n = 17). All patients had received a standard of care biopsy of the prostate, results of which were used to confirm or exclude presence of malignant lesions. We used the linear mixed-effects model-fit by REML to determine the difference between mean values of cancerous tissue and healthy tissue. We found good differentiation between malignant lesions and normal appearing tissue in the peripheral zone based on the mean T2 value. Specifically, the mean T2 value for tissue without malignant lesions was (151.7 ms [95% CI: 146.9-156.5 ms] compared to 80.9 ms for malignant lesions [95% CI: 67.9-79.1 ms]; p < 0.001). Based on this assessment, a limit of 109.2 ms is suggested. Aditionally, a significant correlation was observed between T2 values of the peripheral zone and PI-RADS scores (p = 0.0194). However, no correlation was found between the Gleason Score and the T2 relaxation time. Using REML, we found a difference of -82.7 ms in mean values between cancerous tissue and healthy tissue. We established a cut-off-value of 109.2 ms to accurately differentiate between malignant and non-malignant prostate regions. The addition of T2 mapping sequences to routine imaging could benefit automated lesion detection and facilitate contrast-free multiparametric MRI of the prostate.

Ultrafast T2 and T2* mapping using single-shot spatiotemporally encoded MRI with reduced field of view and spiral out-in-out-in trajectory

BACKGROUND

T2 and T2* mapping are crucial components of quantitative magnetic resonance imaging, offering valuable insights into tissue characteristics and pathology. Single-shot methods can achieve ultrafast T2 or T2* mapping by acquiring multiple readout echo trains. However, the extended echo trains pose challenges, such as compromised image quality and diminished quantification accuracy.

PURPOSE

In this study, we develop a single-shot method for ultrafast T2 and T2* mapping with reduced echo train length.

METHODS

The proposed method is based on ultrafast single-shot spatiotemporally encoded (SPEN) MRI combined with reduced field of view (FOV) and spiral out-in-out-in (OIOI) trajectory. Specifically, a biaxial SPEN excitation scheme was employed to excite the spin signal into the spatiotemporal encoding domain. The OIOI trajectory with high acquisition efficiency was employed to acquire signals within targeted reduced FOV. Through non-Cartesian super-resolved (SR) reconstruction, 12 aliasing-free images with different echo times were obtained within 150 ms. These images were subsequently fitted to generate T2 or T2* mapping simultaneously using a derived model.

RESULTS

Accurate and co-registered T2 and T2* maps were generated, closely resembling the reference maps. Numerical simulations demonstrated substantial consistency (R2 > 0.99) with the ground truth values. A mean difference of 0.6% and 1.7% was observed in T2 and T2*, respectively, in in vivo rat brain experiments compared to the reference. Moreover, the proposed method successfully obtained T2 and T2* mappings of rat kidney in free-breathing mode, demonstrating its superiority over multishot methods lacking respiratory navigation.

CONCLUSIONS

The results suggest that the proposed method can achieve ultrafast and accurate T2 and T2* mapping, potentially facilitating the application of T2 and T2* mapping in scenarios requiring high temporal resolution.

Comparison of model-based versus deep learning-based image reconstruction for thin-slice T2-weighted spin-echo prostate MRI

PURPOSE

To compare a previous model-based image reconstruction (MBIR) with a newly developed deep learning (DL)-based image reconstruction for providing improved signal-to-noise ratio (SNR) in high through-plane resolution (1 mm) T2-weighted spin-echo (T2SE) prostate MRI.

METHODS

Large-area contrast and high-contrast spatial resolution of the reconstruction methods were assessed quantitatively in experimental phantom studies. The methods were next evaluated radiologically in 17 subjects at 3.0 Tesla for whom prostate MRI was clinically indicated. For each subject, the axial T2SE raw data were directed to MBIR and to the DL reconstruction at three vendor-provided levels: (L)ow, (M)edium, and (H)igh. Thin-slice images from the four reconstructions were compared using evaluation criteria related to SNR, sharpness, contrast fidelity, and reviewer preference. Results were compared using the Wilcoxon signed-rank test using Bonferroni correction, and inter-reader comparisons were done using the Cohen and Krippendorf tests.

RESULTS

Baseline contrast and resolution in phantom studies were equivalent for all four reconstruction pathways as desired. In vivo, all three DL levels (L, M, H) provided improved SNR versus MBIR. For virtually, all other evaluation criteria DL L and M were superior to MBIR. DL L and M were evaluated as superior to DL H in fidelity of contrast. For 44 of the 51 evaluations, the DL M reconstruction was preferred.

CONCLUSION

The deep learning reconstruction method provides significant SNR improvement in thin-slice (1 mm) T2SE images of the prostate while retaining image contrast. However, if taken to too high a level (DL High), both radiological sharpness and fidelity of contrast diminish.

Preoperative Subtyping of WHO Grade 1 Meningiomas Using a Single-Shot Ultrafast MR T2 Mapping

BACKGROUND

Meningioma subtype is crucial in treatment planning and prognosis delineation, for grade 1 meningiomas. T2 relaxometry could provide detailed microscopic information but is often limited by long scanning times.

PURPOSE

To investigate the potential of T2 maps derived from multiple overlapping-echo detachment imaging (MOLED) for predicting meningioma subtypes and Ki-67 index, and to compare the diagnostic efficiency of two different region-of-interest (ROI) placements (whole-tumor and contrast-enhanced, respectively).

STUDY TYPE

Prospective.

PHANTOM/SUBJECTS

A phantom containing 11 tubes of MnCl2 at different concentrations, eight healthy volunteers, and 75 patients with grade 1 meningioma.

FIELD STRENGTH/SEQUENCE

3 T scanner. MOLED, T2-weighted spin-echo sequence, T2-dark-fluid sequence, and postcontrast T1-weighted gradient echo sequence.

ASSESSMENT

Two ROIs were delineated: the whole-tumor area (ROI1) and contrast-enhanced area (ROI2). Histogram parameters were extracted from T2 maps. Meningioma subtypes and Ki-67 index were reviewed by a neuropathologist according to the 2021 classification criteria.

STATISTICAL TESTS

Linear regression, Bland-Altman analysis, Pearson's correlation analysis, independent t test, Mann-Whitney U test, Kruskal-Wallis test with Bonferroni correction, and multivariate logistic regression analysis with the P-value significance level of 0.05.

RESULTS

The MOLED T2 sequence demonstrated excellent accuracy for phantoms and volunteers (Meandiff  = -1.29%, SDdiff  = 1.25% and Meandiff  = 0.36%, SDdiff  = 2.70%, respectively), and good repeatability for volunteers (average coefficient of variance = 1.13%; intraclass correlation coefficient = 0.877). For both ROI1 and ROI2, T2 variance had the highest area under the curves (area under the ROC curve = 0.768 and 0.761, respectively) for meningioma subtyping. There was no significant difference between the two ROIs (P = 0.875). Significant correlations were observed between T2 parameters and Ki-67 index (r = 0.237-0.374).

DATA CONCLUSION

MOLED T2 maps can effectively differentiate between meningothelial, fibrous, and transitional meningiomas. Moreover, T2 histogram parameters were significantly correlated with the Ki-67 index.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 2.

Retrospective T2 quantification from conventional weighted MRI of the prostate based on deep learning

Purpose

To develop a deep learning-based method to retrospectively quantify T2 from conventional T1- and T2-weighted images.

Methods

Twenty-five subjects were imaged using a multi-echo spin-echo sequence to estimate reference prostate T2 maps. Conventional T1- and T2-weighted images were acquired as the input images. A U-Net based neural network was developed to directly estimate T2 maps from the weighted images using a four-fold cross-validation training strategy. The structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), mean percentage error (MPE), and Pearson correlation coefficient were calculated to evaluate the quality of network-estimated T2 maps. To explore the potential of this approach in clinical practice, a retrospective T2 quantification was performed on a high-risk prostate cancer cohort (Group 1) and a low-risk active surveillance cohort (Group 2). Tumor and non-tumor T2 values were evaluated by an experienced radiologist based on region of interest (ROI) analysis.

Results

The T2 maps generated by the trained network were consistent with the corresponding reference. Prostate tissue structures and contrast were well preserved, with a PSNR of 26.41 ± 1.17 dB, an SSIM of 0.85 ± 0.02, and a Pearson correlation coefficient of 0.86. Quantitative ROI analyses performed on 38 prostate cancer patients revealed estimated T2 values of 80.4 ± 14.4 ms and 106.8 ± 16.3 ms for tumor and non-tumor regions, respectively. ROI measurements showed a significant difference between tumor and non-tumor regions of the estimated T2 maps (P < 0.001). In the two-timepoints active surveillance cohort, patients defined as progressors exhibited lower estimated T2 values of the tumor ROIs at the second time point compared to the first time point. Additionally, the T2 difference between two time points for progressors was significantly greater than that for non-progressors (P = 0.010).

Conclusion

A deep learning method was developed to estimate prostate T2 maps retrospectively from clinically acquired T1- and T2-weighted images, which has the potential to improve prostate cancer diagnosis and characterization without requiring extra scans.

Value of synthetic MRI quantitative parameters in preprocedural evaluation for TRUS/MRI fusion-guided biopsy of the prostate

BACKGROUND

Transrectal ultrasonography (TRUS)/magnetic resonance imaging (MRI) fusion-guided biopsy has a high clinical application value. However, this technique has some limitations, which limit its use in routine clinical practice. Therefore, the selection of suitable proatate lesions for this technique is worthy of our attention. Synthetic MRI (SyMRI) is capable of quantifying multiple relaxation parameters, which might have potential value in preprocedural evaluation for TRUS/MRI fusion-guided biopsy of the prostate. The aim of our study is to examine the value of SyMRI quantitative parameters in preprocedural evaluation for TRUS/MRI fusion-guided biopsy of the prostate.

METHODS

We prospectively selected 148 lesions in 137 patients who underwent prostate biopsy in our hospital. Next, 2-4 needles of TRUS/MRI fusion-guided biopsy combined with 10 needles of system biopsy (SB) were used as the protocol for prostate biopsy. Before biopsy, the MAGiC sequences of the MRI images of the enrolled patients underwent post-processing, and the longitudinal relaxation time (T1), transverse relaxation time (T2), and proton density (PD) were extracted. The biopsy pathology results were used as a gold standard to compare the differences in SyMRI quantitative parameters between benign and malignant prostate lesions in the peripheral and transitional zones. The receiver operating characteristic (ROC) curves were plotted to confirm the optimal SyMRI quantitative parameter for prostate lesion benignancy/malignancy performance, and the cutoff values of these parameters were used for grouping the lesions. The single-needle biopsy prostate cancer (PCa)-positivity rates (number of positive biopsy needles/total biopsy needles) and PCa overall detection rates by TRUS/MRI fusion-guided biopsy and SB were compared in different subgroups.

RESULTS

The T1 and T2 values can determine the benignancy/malignancy of prostate transition lesions(p < 0.01), and the T2 value has a greater diagnostic performance (p = 0.0376). The T2 value can determine the benignancy/malignancy of prostate peripheral lesions. The optimal diagnostic cutoff values for T2 were 77 and 81 ms, respectively. The single-needle PCa positivity rate of TRUS/MRI fusion-guided biopsy was higher than SB for any prostate lesions in different subgroups (p < 0.01). However, only in the subgroup of transition zone lesions with T2 ≤ 77 ms, the PCa overall detection rate of TRUS/MRI fusion-guided biopsy was significantly higher than that of SB (p = 0.031).

CONCLUSION

SyMRI-T2 value can provide a theoretical basis for the selection of suitable lesions for TRUS/MRI fusion-guided biopsy.

The impact of the apparent diffusion coefficient for the early prediction of the treatment response after definitive radiotherapy in prostate cancer patients

PURPOSE

We assessed early changes in apparent diffusion coefficient (ADC) and serum prostate specific antigen (PSA) values after definitive radiotherapy (RT) without androgen deprivation treatment in low- and intermediate-risk prostate cancer (PC) patients.

MATERIALS AND METHODS

The clinical data and ADC parameters of 229 PC patients were retrospectively evaluated. Pre-treatment and post-treatment serum PSA and primary tumor ADC values were calculated. Post-treatment DW-MRI was performed median 4.1 months after completion of definitive RT. The prognostic factors predicting freedom from biochemical failure (FFBF) and progression-free survival (PFS) were analyzed using univariable and multivariable analyses.

RESULTS

With a median follow-up time of 80.8 months, the 5-year FFBF and PFS rates were 95.9% and 89.3%, respectively. Eleven patients (4.8%) had PSA relapse, with a median of 34.4 months after the completion of RT. A statistically significant difference in post-treatment ADC values was noted between patients with and without recurrence (0.94 ± 0.07 vs. 1.10 ± 0.20 × 10^-3 mm²/sec; p < 0.001). Patients with a Gleason score (GS) of 6 and low-risk disease had significantly higher post-treatment tumor ADC and PSA levels than patients with a GS of 7 and intermediate-risk disease. The 5-year FFBF rate in patients with tumor ADC ≤ 0.96 × 10^-3 mm²/sec was significantly lower than patients with tumor ADC > 0.96 × 10^-3 mm²/sec (85.5% vs. 100; p < 0.001). In the multivariable analysis, a lower ADC value, GS 4 + 3 and intermediate-risk disease were independent predictors of worse FFBF. In the multivariate analysis, a lower post-treatment ADC value and a GS of 4+3 were significant prognostic factors for a lower PFS.

CONCLUSION

These findings suggest that the post-treatment tumor ADC value could be used for early treatment response evaluation after definitive RT in PC patients.

Improved Quantitative Parameter Estimation for Prostate T2 Relaxometry using Convolutional Neural Networks

This work seeks to evaluate multiple methods for quantitative parameter estimation from standard T2 mapping acquisitions in the prostate. The T2 estimation performance of methods based on neural networks (NN) was quantitatively compared to that of conventional curve fitting techniques. Large physics-based synthetic datasets simulating T2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Ten combinations of different NN architectures, training strategies, and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness. In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst all the methods. On in vivo data, this best-performing method produced low-noise T2 maps and showed the least deterioration with increasing input noise levels. This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.